Challenge 9

Data Import and Packages

library(tidyverse)
library(DT)

names <- read_csv(here::here("supporting_artifacts", 
                             "learning_targets",  
                             "Lab 9", 
                             "StateNames_A.csv"))

datatable(names)

Warning in instance$preRenderHook(instance): It seems your data is too big
for client-side DataTables. You may consider server-side processing: https://
rstudio.github.io/DT/server.html

Part 1: Summarizing and Visualizing Allisons

Question 1

names <- names |> 
  mutate(Sex = Gender)

allisonname <- names |> 
  select(Name, Year, State, Count, Sex) |> 
  group_by(State, Sex) |> 
  filter(Name == "Allison") |> 
  summarize(Count = sum(Count), .groups = "keep") |> 
  pivot_wider(names_from = Sex, values_from = Count) |> 
  mutate(M = coalesce(M, 0))

knitr::kable(allisonname[, 1:3], 
             col.names = c("State", 
                           "Total Sum of Female", 
                           "Total Sum of Male" ),
             "html")

State	Total Sum of Female	Total Sum of Male
AK	232	0
AL	1535	0
AR	1198	0
AZ	1880	0
CA	12413	0
CO	1594	0
CT	1099	0
DC	321	0
DE	294	0
FL	4455	0
GA	3257	0
HI	183	0
IA	1477	0
ID	451	0
IL	5110	0
IN	3067	0
KS	1283	0
KY	1905	20
LA	1209	0
MA	2218	0
MD	2229	0
ME	340	0
MI	4014	0
MN	2374	0
MO	2882	0
MS	817	0
MT	226	0
NC	3435	0
ND	285	0
NE	807	0
NH	412	0
NJ	3052	0
NM	399	0
NV	729	0
NY	5747	0
OH	5487	0
OK	1421	0
OR	1186	0
PA	4307	0
RI	306	0
SC	1228	0
SD	376	0
TN	2488	0
TX	10192	0
UT	1125	0
VA	3220	0
VT	135	0
WA	1956	0
WI	2367	0
WV	813	0
WY	142	0

Question 2

allisonname_F <- names |> 
  filter(Name == "Allison", Sex == "F")

Question 3

allisonname_f_byYear <- allisonname_F |> 
  group_by(Year) |> 
  summarize(Count = sum(Count))

  ggplot(data = allisonname_f_byYear, mapping = aes(x = Year, y = Count)) +
  geom_point() +
    geom_line() +
  labs(title = 'Popularity of the name "Allison" over time')

Part 2: Modeling the Number of Allisons

Question 4

Model1 <- allisonname_f_byYear |> 
  lm(Count ~ Year, data = _)

Question 5

Model1 |> 
  ggplot(mapping = aes(y = Count, x = Year)) +
  geom_point() +
  stat_smooth(method = "lm")

`geom_smooth()` using formula 'y ~ x'

Question 6

lm(Count ~ Year, data = allisonname_f_byYear)

Call:
lm(formula = Count ~ Year, data = allisonname_f_byYear)

Coefficients:
(Intercept)         Year  
   209689.8       -101.5  

y-hat (estimated Count of Allisons) = 209,689.8 - 101.5 (Year)

Question 7

Model1 |> 
  broom::augment() |> 
  ggplot(mapping = aes(y = .resid, x = .fitted)) +
  geom_point()

In the plot of the residuals against the fitted values, we do not see any discernible pattern.

Question 8

Our model shows that the name Allison is declining in popularity. Allison is still quite popular as about 5000 newborn babies were given that name in our most recent year of data.

Part 3: Spelling by State

Question 1

names |> 
  filter(Sex == "M", Name %in% c("Allan", "Alan", "Allen")) |> 
  group_by(Year, Name) |> 
  summarize(Count = sum(Count)) |> 
  ggplot(mapping = aes(x = Year, y = Count, color = Name)) +
    geom_point() +
    geom_line() +
  labs(title = 'Popularity of the name "Allen, Allan, Alan" over time')

Question 2

alan_name_M <- names |> 
  filter(Sex == "M", Name %in% c("Allan", "Alan", "Allen"),
         Year == 2000, State %in% c("PA", "CA")) |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  select(State, Alan, Allen, Allan)
alan_name_M

# A tibble: 2 × 4
  State  Alan Allen Allan
  <chr> <dbl> <dbl> <dbl>
1 CA      579   176   131
2 PA       51    56    12

knitr::kable(alan_name_M[, 1:4], 
             col.names = c("State",
                           "Count of Alan", 
                           "Count of Allen", 
                           "Count of Allan"),
             "html")

State	Count of Alan	Count of Allen	Count of Allan
CA	579	176	131
PA	51	56	12

Question 3

alan_name_M_per <- names |> 
  filter(Sex == "M", Name %in% c("Allan", "Alan", "Allen"),
         Year == 2000, State %in% c("PA", "CA")) |> 
  group_by(State) |> 
  mutate(Count = Count/sum(Count)) |> 
  pivot_wider(names_from = Name, values_from = Count) |> 
  select(State, Alan, Allen, Allan)
alan_name_M_per

# A tibble: 2 × 4
# Groups:   State [2]
  State  Alan Allen Allan
  <chr> <dbl> <dbl> <dbl>
1 CA    0.653 0.199 0.148
2 PA    0.429 0.471 0.101

knitr::kable(alan_name_M_per[, 1:4], 
             col.names = c("State", 
                           "Percent by State named Alan", 
                           "Percent by State named Allen", 
                           "Percent by State named Allan") , 
             "html") %>%
  kableExtra::kable_styling(latex_options = "striped", font_size = 13)%>%
  kableExtra::row_spec(1:2, color = 'white', background = 'black')

State	Percent by State named Alan	Percent by State named Allen	Percent by State named Allan
CA	0.6534989	0.1986456	0.1478555
PA	0.4285714	0.4705882	0.1008403